• Journal of KIISE
• /
• v.44 no.1
• /
• pp.51-56
• /
• 2017

The research area for solving question answering (QA) problems using artificial intelligence models is in a methodological transition period, and one such architecture, the dynamic memory network (DMN), is drawing attention for two key attributes: its attention mechanism defined by neural network operations and its modular architecture imitating cognition processes during QA of human. In this paper, we increased accuracy of the inferred answers, by adapting an automatic data augmentation method for lacking amount of training data, and by improving the ability of time perception. The experimental results showed that in the 1K-bAbI tasks, the modified DMN achieves 89.21% accuracy and passes twelve tasks which is 13.58% higher with passing four more tasks, as compared with one implementation of DMN. Additionally, DMN's word embedding vectors form strong clusters after training. Moreover, the number of episodic passes and that of supporting facts shows direct correlation, which affects the performance significantly.

• Radiation Oncology Journal
• /
• v.8 no.2
• /
• pp.151-154
• /
• 1990

The acute effects of variable dos rates to total body irradiation (TBI) were investigaed with 600 cGy of single exposure in the mice as a preclinical model. Total 80 mice (ICR) were used. Twenty of which sewed as controls, receiving no irradiation. All irradiated mice showed a universal decline in their weight and white blood cell count. The degree of weight loss and leukopenia were similar at 3 different dos rate but slightly prominent with 15 cGy/minute group. The degree of recovery among the groups showed no dose rate dependence. Our results suggest that TBI with 15 cGy/mimute may be applicable for clinical therapy with careful evaluation of patient's condition.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.983-987
• /
• 2009

One of the critical themes in the language acquisition is its exposure to linguistic environments. Linguistic environments, which interact with infants, include not only human beings such as its parents but also artificially crafted linguistic media as their functioning elements. An infant learns a language by exploring these extensive language environments around it. Based on such large linguistic data exposure, we propose a machine learning based method on the cognitive mechanism that simulate flexibly and appropriately infant's language learning. The infant's initial stage of language learning comes with sentence learning and creation, which can be simulated by exposing it to a language corpus. The core of the simulation is a memory-based learning model which has language hypernetwork structure. The language hypernetwork simulates developmental and progressive language learning using the structure of new data stream through making it representing of high level connection between language components possible. In this paper, we simulates an infant's gradual and developmental learning progress by training language hypernetwork gradually using 32,744 sentences extracted from video scripts of commercial animation movies for children.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.5
• /
• pp.1265-1270
• /
• 2008

In the parts including a vehicle, standard and contents are different according to type of automobile. Although the parts are same, the quality and requirement all are different according to vehicle production version. Also the business is shared at each department in a production line. So if a part is changed, each team or the department must recognize information which is changed. But currently if the event can occur at like this each department, because of parts management through handwork, the unification of information is difficult. Therefore in this paper, we applied POP systems at the automobile part enterprise and constructed POP based the automobile part productive integrated management system. This system supported productive information from mechanical, equipment, worker, and products in real-time and data update also is processed automatically. When this system is introduced, work time and cost remarkably will be reduced.

• Journal of Navigation and Port Research
• /
• v.42 no.4
• /
• pp.277-282
• /
• 2018

Recently, the Vessel Traffic Service (VTS) coverage has expanded to include coastal areas following the increased attention on vessel traffic safety. However, it has increased the workload on the VTS operators. In some cases, when the traffic volume increases sharply during the rush hour, the VTS operator may not be aware of the risks. Therefore, in this paper, we proposed a new method to recognize ship movement anomalies automatically to support the VTS operator's decision-making. The proposed method generated traffic pattern model without any category information using the unsupervised learning algorithm.. The anomaly score can be calculated by classification and comparison of the trained model. Finally, we reviewed the experimental results using a ship-handling simulator and the actual trajectory data to verify the feasibility of the proposed method.

• The KIPS Transactions:PartB
• /
• v.10B no.7
• /
• pp.795-802
• /
• 2003

To live autonomously, intelligent agents such as robots or virtual characters need ability that recognizes given environment, and learns and chooses adaptive actions. So, we propose an action selection/learning mechanism in intelligent agents. The proposed mechanism employs a hybrid system which integrates a behavior-based method using the reinforcement learning and a cognitive-based method using the symbolic learning. The characteristics of our mechanism are as follows. First, because it learns adaptive actions about environment using reinforcement learning, our agents have flexibility about environmental changes. Second, because it learns environmental factors for the agent's goals using inductive machine learning and association rules, the agent learns and selects appropriate actions faster in given surrounding and more efficiently in extended surroundings. Third, in implementing the intelligent agents, we considers only the recognized states which are found by a state detector rather than by all states. Because this method consider only necessary states, we can reduce the space of memory. And because it represents and processes new states dynamically, we can cope with the change of environment spontaneously.

• School Mathematics
• /
• v.12 no.3
• /
• pp.323-335
• /
• 2010

Linear algebra is not only applied comprehensively in the branches of mathematics such as algebra, analytics, and geometry but also utilized for finding solutions in various fields such as aeronautical engineering, electronics, biology, geology, mechanics and etc. Therefore, linear algebra should be easy and comfortable for not only mathematics majors but also for general students as well. However, most find it difficult to learn linear algebra. Why is it so? It is because many studying linear algebra fail to achieve a correct understanding or attain erroneous concepts through misleading knowledge they already have. Such cases cause learning disability and mistakes. This research suggests more effective method of teaching by analyzing difficulty and errors made in learning system of linear equations.

• Journal of Radiation Protection and Research
• /
• v.25 no.4
• /
• pp.217-221
• /
• 2000

Radiotheraphy may be considered as one of the most effective treatments for digestive tumors. This procedure has major side effects, especially in fast growing tissues like intestinal mucosa. For this reason, the morphological changes in mouse jejunal villi after whole body ${\gamma}-irradiation$ were analysed. Four week old ICR male mice were irradiatied with 6.5Gy or 12Gy of whole body ${\gamma}-irradiation$ and were sacrificed 3 days later. Jejunum among intestine were taken for morphology. Samples were carried out dehydration process and sliced sample covered with paraffin was hold on the slide and then light microscopy was observed by Hematoxylin & Eosin staining. villi at both irradiated doses were showed that the length of villi were shortened and thickened and that lumen were expanded in comparison with non-irradiated group. Since willi have an important role in digestion and very sensitive to radiation from this test, it has a role of test parameter for finding radioprotectors as well as evaluating the biological effect by radiaton.

• Journal of Conservation Science
• /
• v.10 no.1 s.13
• /
• pp.10-20
• /
• 2001

Since the feasibility for the application of laser to the conservation of artworks had been demonstrated by John F. Asmus at 1972 it was known from many experiments that laser cleaning technology Provided superior characteristics over conventional cleaning methods based on mechanical and chemical actions. Then, the research and development of the cleaning technology was carried out strongly in Europe and many successful cleaning applications such as stone, painting, stained glass, paper, leather, and metal have been reported. However this is not familiar as a cleaning tool in the restoration of artworks in oriental countries including Korea. Therefore, this article aims to introduce a laser cleaning technology and its characteristics for the applications to art restoration. The contents in this article include general principles and characteristics of laser, the introduction of laser cleaning technology, and real laser applications for artwork restoration.

• Journal of Internet Computing and Services
• /
• v.12 no.6
• /
• pp.83-94
• /
• 2011

Main researching issue in affective computing is to give a machine the ability to recognize the emotion of a person and to react it properly. Efforts in that direction have mainly focused on facial and oral cues to get emotions. Postures have been recently considered as well. This paper aims to discriminate emotions posture by identifying and measuring the saliency of posture features that play a role in affective expression. To do so, affective postures from human subjects are first collected using a motion capture system, then emotional features in posture are described with spatial ones. Through standard statistical techniques, we verified that there is a statistically significant correlation between the emotion intended by the acting subjects, and the emotion perceived by the observers. Discriminant Analysis are used to build affective posture predictive models and to measure the saliency of the proposed set of posture features in discriminating between 6 basic emotional states. The evaluation of proposed features and models are performed using a correlation between actor-observer's postures set. Quantitative experimental results show that proposed set of features discriminates well between emotions, and also that built predictive models perform well.